HPC C/C++ Parallel Development

I’m expanding a high-performance computing initiative and need seasoned C/C++ talent to squeeze every last cycle out of our code. The core of the work revolves around designing, profiling, and hardening parallel processing routines that will run on Linux/Unix clusters. You’ll be free to choose the right mix of pthreads, OpenMP, MPI, CUDA, or similar frameworks as long as the end result is fast, deterministic, and fully verifiable.

Here’s the environment you’ll step into: a mature codebase written almost entirely in modern C and C++, backed by rigorous data-structure design, multithreaded execution, and an SDLC that values deep debugging over quick patches. I handle planning, testing resources, and CI; you focus on writing clean, well-documented modules and driving their performance to the limit.

Deliverables
• Optimised C/C++ source files for the assigned computation kernels
• Profiling reports that demonstrate measurable speed-ups over the baseline
• Unit and integration tests that prove functional correctness across threads

Acceptance criteria
Performance gains must be reproducible on our reference hardware, pass Valgrind and ThreadSanitizer checks, and integrate without regressions into our Git workflow.

The engagement is remote, billed hourly, and ideal for developers with 4-12 years of real-world experience who thrive on algorithmic challenges and large-scale optimisation. If that sounds like you, let’s talk.